Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3955 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.6234. Min Act: -0.1700
Data Index: 1167604 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.5921. Min Act: -0.1700
Data Index: 2233774 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4984. Min Act: -0.1700
Data Index: 8501934 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4984. Min Act: -0.1700
Data Index: 4470550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4671. Min Act: -0.1700
Data Index: 1974297 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4671. Min Act: -0.1700
Data Index: 6171665 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4671. Min Act: -0.1700
Data Index: 2866782 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4671. Min Act: -0.1700
Data Index: 1396281 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4671. Min Act: -0.1700
Data Index: 8535583 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4359. Min Act: -0.1700
Data Index: 1024302 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4359. Min Act: -0.1700
Data Index: 2273374 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4359. Min Act: -0.1700
Data Index: 5842039 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4359. Min Act: -0.1700
Data Index: 3055601 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4359. Min Act: -0.1700
Data Index: 7384432 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4359. Min Act: -0.1700
Data Index: 7948366 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4046. Min Act: -0.1700
Data Index: 5842038 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4046. Min Act: -0.1700
Data Index: 2876401 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4046. Min Act: -0.1700
Data Index: 6739637 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4046. Min Act: -0.1700
Data Index: 3290847 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6234. Min Range: -4.6234
Max Act: 4.4046. Min Act: -0.1700
Data Index: 2983904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19